HN Explorer

covi

↗ HN profile [ 83.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. VRAM Ghost Busting: Who You Gonna Close()? (hcompany.ai)
    1 points 0
  2. SkyPilot Sandboxes: Run Agent Code on Your Own Kubernetes, at Scale (blog.skypilot.co)
    6 points 0
  3. RL Doesn't Work on Slurm (blog.skypilot.co)
    5 points 0
  4. SkyPilot: One system to use and manage all AI compute (K8s, 20 clouds, Slurm) (github.com)
    15 points 2
  5. The Evolution of AI Job Orchestration (blog.skypilot.co)
    2 points 0
  6. Large-Scale AI Batch Inference: 9x Faster Embedding Generation (blog.skypilot.co)
    1 points 0
  7. Abusing SQLite to Handle Concurrency (blog.skypilot.co)
    2 points 0
  8. Using DeepSeek R1 for RAG: Do's and Don'ts (blog.skypilot.co)
    13 points 2
  9. Building Large-Scale Image Search Using VectorDB and OpenAI Clip (blog.skypilot.co)
    3 points 2
  10. Fungible cloud compute and storage: AI training on any cloud (tigrisdata.com)
    2 points 0
  11. Getting $1M cloud credits for AI startups – and using them wisely (blog.skypilot.co)
    1 points 0
  12. You Ran the Operational Database on What? Testing Spot Instances (cockroachlabs.com)
    3 points 1
  13. Can Multi-Modal LLMs "See" Images? A Deep Dive with ASCII Art (blog.skypilot.co)
    3 points 0
  14. Embarrassingly parallel batch jobs on multiple clouds or regions (skypilot.readthedocs.io)
    1 points 0
  15. Llama 3.1 finetuning on your own data and infra, without vendor lock-in (blog.skypilot.co)
    2 points 0
  16. Guide: Finetune Llama 3.1 on your infra (github.com)
    5 points 0
  17. AI on Kubernetes Without the Pain (blog.skypilot.co)
    2 points 0
  18. Dagster and SkyPilot: Orchestrating LLM training cost-effectively (dagster.io)
    3 points 0
  19. Inflection CEO Left, Became CEO of Microsoft AI (twitter.com)
    5 points 0
  20. SkyServe: A cost-efficient, multi-region/cloud library for serving GenAI models (blog.skypilot.co)
    4 points 0
  21. SGLang: Fast and Expressive LLM Inference with RadixAttention for 5x Throughput (github.com)
    2 points 0
  22. SkyServe: 50% Cheaper AI Serving on Any Cloud with High Availability (blog.skypilot.co)
    5 points 0
  23. Tigris: Globally Distributed S3-Compatible Object Storage (tigrisdata.com)
    6 points 0
  24. Scaling Mixtral LLM Serving Across Clouds (blog.skypilot.co)
    2 points 0
  25. Covariant: Moving from on-prem to the cloud for 4x faster AI development (blog.skypilot.co)
    4 points 1